{"id":"https://openalex.org/W2140400559","doi":"https://doi.org/10.1109/icassp.2004.1326018","title":"Improving phoneme recognition of telephone quality speech","display_name":"Improving phoneme recognition of telephone quality speech","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2140400559","doi":"https://doi.org/10.1109/icassp.2004.1326018","mag":"2140400559"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073785112","display_name":"Qiang Huang","orcid":"https://orcid.org/0000-0002-5455-9454"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]},{"id":"https://openalex.org/I169768744","display_name":"Norwich University","ror":"https://ror.org/04we7d902","country_code":"US","type":"education","lineage":["https://openalex.org/I169768744"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Qiang Huang","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK","[Sch. of Comput. Sci., East Anglia Univ., Norwich, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., East Anglia Univ., Norwich, UK]","institution_ids":["https://openalex.org/I169768744"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101798651","display_name":"Stephen Cox","orcid":"https://orcid.org/0000-0002-4443-1000"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]},{"id":"https://openalex.org/I169768744","display_name":"Norwich University","ror":"https://ror.org/04we7d902","country_code":"US","type":"education","lineage":["https://openalex.org/I169768744"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"S. Cox","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK","[Sch. of Comput. Sci., East Anglia Univ., Norwich, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., East Anglia Univ., Norwich, UK]","institution_ids":["https://openalex.org/I169768744"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18529947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.846875011920929},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8160965442657471},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7015339732170105},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6451419591903687},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5526823401451111},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5458484292030334},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.48440486192703247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45616987347602844},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4552761912345886},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4462416172027588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4164387583732605},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11427080631256104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.846875011920929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8160965442657471},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7015339732170105},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6451419591903687},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5526823401451111},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5458484292030334},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.48440486192703247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45616987347602844},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4552761912345886},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4462416172027588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4164387583732605},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11427080631256104},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2004.1326018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.981.8140","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.981.8140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.cmp.uea.ac.uk/%7Esjc/huang-cox-icassp04.pdf","raw_type":"text"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:23652","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/23652/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W200927961","https://openalex.org/W2088857750","https://openalex.org/W2096421062","https://openalex.org/W2115459718","https://openalex.org/W2117520332","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W4372260574","https://openalex.org/W4383031668"],"abstract_inverted_index":{"There":[0],"are":[1,10,53,58],"some":[2],"speech":[3,75],"understanding":[4],"applications":[5],"in":[6,95,117],"which":[7,96],"training":[8,50],"transcriptions":[9,48],"unavailable,":[11],"and":[12,26,104,107],"hence":[13],"the":[14,19,99,115,118,134,140],"vocabulary":[15],"is":[16,21,45,68,85],"unknown,":[17],"but":[18],"task":[20,44],"to":[22,33,56,113,125,143],"recognise":[23],"key":[24],"words":[25],"phrases":[27],"within":[28],"an":[29,108],"utterance":[30],"rather":[31,64],"than":[32,65],"attempt":[34],"a":[35,43,78,93],"complete,":[36],"accurate":[37],"transcription.":[38],"An":[39],"example":[40],"of":[41,49,73],"such":[42,61],"call-routing,":[46],"when":[47],"utterances":[51],"(which":[52],"very":[54,86],"expensive":[55],"produce)":[57],"unavailable.":[59],"In":[60],"cases,":[62],"phoneme":[63,71,135],"word":[66],"recognition":[67,72],"appropriate.":[69],"However,":[70],"spontaneous":[74,131],"spoken":[76],"by":[77],"large":[79],"multi-accent":[80],"population":[81],"over":[82],"telephone":[83,129],"connections":[84],"inaccurate.":[87],"To":[88],"improve":[89],"accuracy,":[90],"we":[91,97],"describe":[92],"technique":[94],"segment":[98],"waveform":[100],"into":[101],"subword-like":[102],"units":[103],"use":[105],"clustering":[106],"iteratively":[109],"refined":[110],"language":[111],"model":[112],"correct":[114],"errors":[116],"recognised":[119],"phonemes.":[120],"The":[121],"method":[122],"was":[123],"shown":[124],"work":[126],"well":[127],"on":[128],"quality":[130],"speech,":[132],"raising":[133],"accuracy":[136],"from":[137],"28.1%":[138],"after":[139,145],"first":[141],"iteration":[142],"47.3%":[144],"three":[146],"iterations.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}